Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 2169
    Prev
    Next
    INDEX
    Explanations

    imperative verbs indicating actions or instructions

    oai_token-act-pair · gpt-3.5-turbo

    commands or suggestions made to an audience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĹ
    -0.64
     breaching
    -0.61
     wheelchair
    -0.61
    ITE
    -0.61
     bottleneck
    -0.60
    PATH
    -0.60
     record
    -0.60
    ELF
    -0.59
    mith
    -0.58
    cler
    -0.58
    POSITIVE LOGITS
    ings
    1.00
     Yourself
    0.86
    ership
    0.85
    quartered
    0.82
    ington
    0.82
     yourselves
    0.81
    anon
    0.80
    amaz
    0.79
     Quote
    0.79
    ables
    0.77
    Activations Density 0.205%

    No Known Activations